Re: [viewvc-dev] Re: [viewvc-users] Don't display binary files

Index: viewvc.conf.dist
===================================================================
--- viewvc.conf.dist    (revision 2047)
+++ viewvc.conf.dist    (working copy)
@@ -269,6 +269,13 @@
 # Possible values: "tar", "annotate", "co", "markup", "roots"
 allowed_views = markup, annotate, roots

+# Don't use the svn:mime-type property to determine how to display a
+# file in the markup view.  This is helpful when, for example, an image
+# has svn:mime-type set to application/octet-stream.  If ViewVC tries
+# to display the image using the mime type application/octet-stream,
+# the image will look unrecognizeable.
+ignore_svn_mimetype = 0
+
 # authorizer: The name of the ViewVC authorizer plugin to use when
 # authorizing access to repository contents.  This value must be the
 # name of a Python module addressable as vcauth.MODULENAME (most
Index: templates/file.ezt
===================================================================
--- templates/file.ezt  (revision 2047)
+++ templates/file.ezt  (working copy)
@@ -102,5 +102,12 @@
 [end]
 [end]

+[if-any is_viewable]
+[else]
+<h3>
+<em>Non-viewable file contents hidden</em>
+</h3>
+[end]
+
 [include "include/props.ezt"]
 [include "include/footer.ezt"]
Index: lib/viewvc.py
===================================================================
--- lib/viewvc.py       (revision 2047)
+++ lib/viewvc.py       (working copy)
@@ -972,6 +972,24 @@
 def is_text(mime_type):
   return not mime_type or mime_type[:5] == 'text/'

+text_characters = "".join(map(chr, range(32, 127)) + list("\n\r\t\b"))
+_null_trans = string.maketrans("", "")
+
+def istext(s):
+  if "\0" in s:
+    return 0
+
+  if not s:  # Empty files are considered text
+    return 1
+
+  # Get the non-text characters (maps a character to itself then
+  # use the 'remove' option to get rid of the text characters.)
+  t = s.translate(_null_trans, text_characters)
+
+  # If more than 30% non-text characters, then
+  # this is considered a binary file
+  return float(len(t))/len(s) <= 0.30
+
 def is_cvsroot_path(roottype, path_parts):
   return roottype == 'cvs' and path_parts and path_parts[0] == 'CVSROOT'

@@ -1465,7 +1483,8 @@
   mime_type = None
   if not path_parts:
     return None
-  if request.roottype == 'svn':
+  if request.roottype == 'svn' and \
+     not request.cfg.options.ignore_svn_mimetype:
     try:
       itemprops = request.repos.itemprops(path_parts, rev)
       mime_type = itemprops.get('svn:mime-type')
@@ -1481,6 +1500,7 @@
   lines = fp = image_src_href = None
   annotation = None
   revision = None
+  is_viewable = None
   mime_type = calculate_mime_type(request, path, rev)

   # Is this a viewable image type?
@@ -1493,6 +1513,7 @@
     annotation = 'binary'
     image_src_href = request.get_url(view_func=view_checkout,
                                      params={'revision': rev}, escape=1)
+    is_viewable = True

   # Not a viewable image.
   else:
@@ -1513,10 +1534,18 @@
     if check_freshness(request, None, revision, weak=1):
       fp.close()
       return
-    lines = markup_stream_pygments(request, cfg, blame_source, fp,
-                                   path[-1], mime_type)
-    fp.close()

+    # Make sure its a text file.
+    if istext(fp.read(512)):
+      is_viewable = True
+      fp.close()
+      fp, revision = request.repos.openfile(path, rev)
+      lines = markup_stream_pygments(request, cfg, blame_source, fp,
+                                     path[-1], mime_type)
+      fp.close()
+    else:
+      is_viewable = False
+
   data = common_template_data(request, revision)
   data.update({
     'mime_type' : mime_type,
@@ -1538,6 +1567,7 @@
     'lines' : lines,
     'properties' : get_itemprops(request, path, rev),
     'annotation' : annotation,
+    'is_viewable' : ezt.boolean(is_viewable),
     })

   if cfg.options.show_log_in_markup: